Domain 3 · 19% of the exam · 12 of 63 questions
Integration
The heaviest domain on the exam and the most technical. Retrieval pipelines, tool and agent configuration, authentication across a system that acts on a user's behalf, protocol choice between MCP and a direct integration, and the latency and observability costs of all of it. If you are budgeting revision time by weight, this is where it goes.
every one of the 38 pool items in this domain · explanations as you go · free
The 8 objectives in this domain
A real score report grades each of these separately, so a weakness here is addressable at this level rather than by re-reading the whole domain. Each one has its own drill.
- 3.1Evaluate tool/agent configuration for capability bloat5 questions
- 3.2Analyze authentication and authorization requirements to identify security gaps5 questions
- 3.3Evaluate accuracy-latency trade-offs and justify configuration decisions5 questions
- 3.4Analyze observability challenges and select monitoring strategies at scale5 questions
- 3.5Design a RAG pipeline with appropriate chunking and indexing strategies5 questions
- 3.6Apply retrieval strategies matched to data shape and query pattern5 questions
- 3.7Evaluate connection protocols and select the appropriate integration mechanism (MCP, API/CLI, agent-to-agent)4 questions
- 3.8Evaluate progressive discovery vs. monolithic context strategy4 questions
The other 6 domains
Drilling one domain tells you about one domain. A full-length timed mock in blueprint proportions is what produces a score you can read.
Sit a timed mock →